PAN(Zheng et al., [2017a])

Reported on 4 benchmarks across 1 task · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision4 results

Person Re-IdentificationonCUHK03 labeled
MAP· 2017-07-03
35
best: 89.29 (Weakly Pre-training (ResNet101+RK))
Pedestrian Alignment Network for Large-scale Person Re-identification arXiv:1707.00408
Person Re-IdentificationonCUHK03 labeled
Rank-1· 2017-07-03
36.9
best: 87.86 (Weakly Pre-training (ResNet101+RK))
Pedestrian Alignment Network for Large-scale Person Re-identification arXiv:1707.00408
Person Re-IdentificationonCUHK03 (detected)
MAP· 2017-07-03
34
best: 43.8 (PAN+re-rank)
Pedestrian Alignment Network for Large-scale Person Re-identification arXiv:1707.00408
Person Re-IdentificationonCUHK03 (detected)
Rank-1· 2017-07-03
36.3
best: 41.9 (PAN+re-rank)
Pedestrian Alignment Network for Large-scale Person Re-identification arXiv:1707.00408